PROD TYPE: COM PP:1 col fig nil PR2195 DTD VER: ED: PrathibaPAGN: Vidya SCAN: global

Niveau: Secondaire, Lycée, Terminale
UN CO RR EC TE D PR OO F PROD. TYPE: COM PP:1-12 (col.fig.: nil) PR2195 DTD VER: 5.0.1 ED: PrathibaPAGN: Vidya -- SCAN: global ARTICLE IN PRESS Pattern Recognition ( ) – 1 Semi-supervised statistical region refinement for color image segmentation3 Richard Nocka,?, Frank Nielsenb aGRIMAAG-Département Scientifique Interfacultaire, Université des Antilles-Guyane, Campus de Schoelcher, BP 7209, 97275 Schoelcher,5 Martinique, France bSony Computer Science Laboratories, Inc., 3-14-13 Higashi Gotanda, Shinagawa-Ku, Tokyo 141-0022, Japan7 Received 9 August 2004 Abstract9 Some authors have recently devised adaptations of spectral grouping algorithms to integrate prior knowledge, as constrained eigenvalues problems. In this paper, we improve and adapt a recent statistical region merging approach to this task, as a non-11 parametric mixture model estimation problem. The approach appears to be attractive both for its theoretical benefits and its experimental results, as slight bias brings dramatic improvements over unbiased approaches on challenging digital pictures.13 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved. Keywords: Image segmentation; Semi-supervised grouping15 1. Introduction Grouping is the discovery of intrinsic clusters in data [1].

• algorithm


• regions obtained


• well-known benchmark


• single event's


• grouping


• segmentation


• algorithm probabilistic-sorted image11